Startups and Consumer Purchase Behavior: Application of Support Vector Machine Algorithm

Round 1

Reviewer 1 Report

Please see the attached referee report.

Comments for author File: Comments.pdf

Author Response

Dear reviewer,

Thank you for the constructive comments. We considered your comments as it is mentioned in the attached file.

Best regards,

Author Response File: Author Response.docx

Reviewer 2 Report

This paper evaluates the impact of startup technology innovations and CRM performance on customer participation, value co-creation, and consumer purchase behavior. Proposed hypotheses were tested using SEM and SmartPLS 3 techniques. SVM model was applied for verification of model accuracy. Proposed approach is not very novel in the study.

Comments and suggestions:

1. All abbreviations must be given a full name when appear for the first time (marked in the text).

2. No reference to Figure 1 in the text.

3. There are too many hypothesis, you should just give 2-3 main research  goals of the paper.

4. There was mentioned 466 respondents questionanires, but only 406 reported in the table 1. There is no information about the mechanism of sample selection. We don't know if we can generalize results or not.

5. Python codes in appendix are not value added.

6. A lot of CrossRef in the References.

Comments for author File: Comments.pdf

Author Response

Dear reviewer,

Thank you for the constructive comments. We considered your comments as it is mentioned in the attached file.

Best regards,

Author Response File: Author Response.docx

Reviewer 3 Report

This paper Startups and consumer purchase behavior: Application of support vector machine algorithm evaluates the impact of startup technology innovations and CRM performance on customer general behavior. This is an interesting study and could also be applied to a different type of problems and also to other areas, where the data is available. Still, there are some minor issues related with the paper that need to be addressed before it can be considered for publishing. Explain, if the results of SVM method is interpretable in user friendly way, for example if it is possible to find out from learned prediction model, which variables used in prediction models have the biggest influence on predicted results. Check those two papers (10.1016/j.trd.2018.11.015 and 10.1016/j.foreco.2018.05.039) and write few sentences about interpretability of used models. Figures in general should be better quality, especially the text is not visible well, when article is printed. In lines 336 and 337 some brackets are missing. Did you use any cross validation in learning of SVM model? There are also few mistakes in paper, because of that I recommend a native speaker for proofreading of the paper.

Author Response

Dear reviewer,

Thank you for the constructive comments. We considered your comments as it is mentioned in the attached file.

Best regards,

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

I accept your response for review and changes made in the paper.